{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/named-entity-recognition-1","name":"Named Entity Recognition","slug":"named-entity-recognition-1","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2560,"papers_with_code":969,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":20,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/conll-2003","name":"CoNLL 2003","full_name":"","num_papers_in_archive":755},{"url":"/dataset/ontonotes-5-0","name":"OntoNotes 5.0","full_name":"","num_papers_in_archive":254},{"url":"/dataset/conll-1","name":"CoNLL","full_name":"","num_papers_in_archive":187},{"url":"/dataset/ncbi-disease-1","name":"NCBI Disease","full_name":"","num_papers_in_archive":154},{"url":"/dataset/scierc","name":"SciERC","full_name":"","num_papers_in_archive":134},{"url":"/dataset/conll-2012-1","name":"CoNLL-2012","full_name":"","num_papers_in_archive":89},{"url":"/dataset/few-nerd","name":"Few-NERD","full_name":"Few-NERD","num_papers_in_archive":77},{"url":"/dataset/wikiann-1","name":"WikiANN","full_name":"PAN-X","num_papers_in_archive":72},{"url":"/dataset/masakhaner","name":"MasakhaNER","full_name":"","num_papers_in_archive":56},{"url":"/dataset/gum","name":"GUM","full_name":"Georgetown University Multilayer corpus","num_papers_in_archive":13},{"url":"/dataset/nuner","name":"NuNER","full_name":"","num_papers_in_archive":4},{"url":"/dataset/latamxix","name":"LatamXIX","full_name":"19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","num_papers_in_archive":2},{"url":"/dataset/coneco","name":"CoNECo","full_name":"Complex Named Entity Corpus","num_papers_in_archive":1},{"url":"/dataset/financial-dynamic-knowledge-graph","name":"Financial Dynamic Knowledge Graph","full_name":"","num_papers_in_archive":1},{"url":"/dataset/first-harem","name":"First HAREM","full_name":"Primeiro HAREM","num_papers_in_archive":1},{"url":"/dataset/mini-harem","name":"Mini HAREM","full_name":"","num_papers_in_archive":1},{"url":"/dataset/arf","name":"ARF","full_name":"Artificial Relationships in Fiction","num_papers_in_archive":0},{"url":"/dataset/popcorn","name":"POPCORN","full_name":"POPCORN: Fictional and Synthetic Intelligence Reports for Named Entity Recognition and Relation Extraction Tasks","num_papers_in_archive":0},{"url":"/dataset/second-harem","name":"Second HAREM","full_name":"Segundo HAREM","num_papers_in_archive":0},{"url":"/dataset/sigarra-news-corpus","name":"SIGARRA News Corpus","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":26,"rows_per_page":100,"shown":100,"of":2560,"of_with_code":969,"tagged_in_all":2560,"counts":{"archive_papers_tagged":2560,"with_a_code_link":969,"where_syntology_ran_a_sample":118,"not_listed_spam_title":0,"listed":2560,"listed_where_code_ran":118,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":98,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":98,"listed_every_run_a_failure_of_syntologys_instrument":20,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","repositories_listed":534,"syntology":{"n":659,"n_ran":300,"n_constructed":75,"n_ran_checked":234,"n_instrument":66,"n_unverified":359,"n_honours":18,"n_violates":5,"n_no_contract":211,"n_pointer_only":164,"phrase":"300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified","sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}},"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/neural-architectures-for-named-entity","slug":"neural-architectures-for-named-entity","title":"Neural Architectures for Named Entity Recognition","date":"2016-03-04","arxiv_id":"1603.01360","repositories_listed":43,"syntology":{"n":36,"n_ran":29,"n_constructed":0,"n_ran_checked":22,"n_instrument":7,"n_unverified":7,"n_honours":2,"n_violates":1,"n_no_contract":19,"n_pointer_only":6,"phrase":"29 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/neural-architectures-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/1603.01360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.01360"}},"official":{"repos":["clab/stack-lstm-ner","glample/tagger"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/end-to-end-sequence-labeling-via-bi","slug":"end-to-end-sequence-labeling-via-bi","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","date":"2016-03-04","arxiv_id":"1603.01354","repositories_listed":25,"syntology":{"n":24,"n_ran":24,"n_constructed":0,"n_ran_checked":22,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":20,"n_pointer_only":3,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-sequence-labeling-via-bi#ran","syntology_url":"https://syntology.ai/paper/1603.01354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.01354"}},"official":null}},{"url":"/paper/ernie-enhanced-representation-through","slug":"ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","arxiv_id":"1904.09223","repositories_listed":19,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ernie-enhanced-representation-through#ran","syntology_url":"https://syntology.ai/paper/1904.09223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09223"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/biobert-a-pre-trained-biomedical-language","slug":"biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","arxiv_id":"1901.08746","repositories_listed":19,"syntology":{"n":25,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/biobert-a-pre-trained-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/1901.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08746"}},"official":{"repos":["dmis-lab/biobert","naver/biobert-pretrained"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/named-entity-recognition-with-bidirectional","slug":"named-entity-recognition-with-bidirectional","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","date":"2015-11-26","arxiv_id":"1511.08308","repositories_listed":14,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/named-entity-recognition-with-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1511.08308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.08308"}},"official":null}},{"url":"/paper/nezha-neural-contextualized-representation","slug":"nezha-neural-contextualized-representation","title":"NEZHA: Neural Contextualized Representation for Chinese Language Understanding","date":"2019-08-31","arxiv_id":"1909.00204","repositories_listed":10,"syntology":null},{"url":"/paper/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","repositories_listed":9,"syntology":{"n":10,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/luke-deep-contextualized-entity#ran","syntology_url":"https://syntology.ai/paper/2010.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01057"}},"official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/camembert-a-tasty-french-language-model","slug":"camembert-a-tasty-french-language-model","title":"CamemBERT: a Tasty French Language Model","date":"2019-11-10","arxiv_id":"1911.03894","repositories_listed":8,"syntology":null},{"url":"/paper/a-unified-mrc-framework-for-named-entity","slug":"a-unified-mrc-framework-for-named-entity","title":"A Unified MRC Framework for Named Entity Recognition","date":"2019-10-25","arxiv_id":"1910.11476","repositories_listed":8,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-unified-mrc-framework-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/1910.11476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11476"}},"official":{"repos":["ShannonAI/mrc-for-flat-nested-ner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/few-nerd-a-few-shot-named-entity-recognition","slug":"few-nerd-a-few-shot-named-entity-recognition","title":"Few-NERD: A Few-Shot Named Entity Recognition Dataset","date":"2021-05-16","arxiv_id":"2105.07464","repositories_listed":7,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/few-nerd-a-few-shot-named-entity-recognition#ran","syntology_url":"https://syntology.ai/paper/2105.07464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.07464"}},"official":{"repos":["thunlp/Few-NERD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tener-adapting-transformer-encoder-for-name","slug":"tener-adapting-transformer-encoder-for-name","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","date":"2019-11-10","arxiv_id":"1911.04474","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tener-adapting-transformer-encoder-for-name#ran","syntology_url":"https://syntology.ai/paper/1911.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04474"}},"official":{"repos":["fastnlp/TENER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-natural-language-decathlon-multitask","slug":"the-natural-language-decathlon-multitask","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","date":"2018-06-20","arxiv_id":"1806.08730","repositories_listed":6,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-natural-language-decathlon-multitask#ran","syntology_url":"https://syntology.ai/paper/1806.08730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.08730"}},"official":{"repos":["salesforce/decaNLP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/xiyan-sql-a-multi-generator-ensemble","slug":"xiyan-sql-a-multi-generator-ensemble","title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","date":"2024-11-13","arxiv_id":"2411.08599","repositories_listed":5,"syntology":null},{"url":"/paper/crossner-evaluating-cross-domain-named-entity","slug":"crossner-evaluating-cross-domain-named-entity","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","date":"2020-12-08","arxiv_id":"2012.04373","repositories_listed":5,"syntology":null},{"url":"/paper/biomedical-and-clinical-english-model","slug":"biomedical-and-clinical-english-model","title":"Biomedical and Clinical English Model Packages in the Stanza Python NLP Library","date":"2020-07-29","arxiv_id":"2007.14640","repositories_listed":5,"syntology":null},{"url":"/paper/stanza-a-python-natural-language-processing","slug":"stanza-a-python-natural-language-processing","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","date":"2020-03-16","arxiv_id":"2003.07082","repositories_listed":5,"syntology":{"n":30,"n_ran":16,"n_constructed":8,"n_ran_checked":10,"n_instrument":6,"n_unverified":14,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":28,"phrase":"16 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/stanza-a-python-natural-language-processing#ran","syntology_url":"https://syntology.ai/paper/2003.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07082"}},"official":{"repos":["stanfordnlp/stanza"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/klue-korean-language-understanding-evaluation","slug":"klue-korean-language-understanding-evaluation","title":"KLUE: Korean Language Understanding Evaluation","date":"2021-05-20","arxiv_id":"2105.09680","repositories_listed":4,"syntology":null},{"url":"/paper/neural-modeling-for-named-entities-and","slug":"neural-modeling-for-named-entities-and","title":"Neural Modeling for Named Entities and Morphology (NEMO^2)","date":"2020-07-30","arxiv_id":"2007.15620","repositories_listed":4,"syntology":null},{"url":"/paper/arabert-transformer-based-model-for-arabic","slug":"arabert-transformer-based-model-for-arabic","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","date":"2020-02-28","arxiv_id":"2003.00104","repositories_listed":4,"syntology":null},{"url":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","slug":"dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dice-loss-for-data-imbalanced-nlp-tasks#ran","syntology_url":"https://syntology.ai/paper/1911.02855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02855"}},"official":{"repos":["ShannonAI/dice_loss_for_NLP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/entity-relation-and-event-extraction-with","slug":"entity-relation-and-event-extraction-with","title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","date":"2019-09-08","arxiv_id":"1909.03546","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/entity-relation-and-event-extraction-with#ran","syntology_url":"https://syntology.ai/paper/1909.03546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03546"}},"official":{"repos":["dwadden/dygiepp"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/cutie-learning-to-understand-documents-with","slug":"cutie-learning-to-understand-documents-with","title":"CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor","date":"2019-03-29","arxiv_id":"1903.12363","repositories_listed":4,"syntology":null},{"url":"/paper/few-shot-learning-for-named-entity","slug":"few-shot-learning-for-named-entity","title":"Few-shot Learning for Named Entity Recognition in Medical Text","date":"2018-11-13","arxiv_id":"1811.05468","repositories_listed":4,"syntology":null},{"url":"/paper/an-incremental-parser-for-abstract-meaning","slug":"an-incremental-parser-for-abstract-meaning","title":"An Incremental Parser for Abstract Meaning Representation","date":"2016-08-22","arxiv_id":"1608.06111","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-incremental-parser-for-abstract-meaning#ran","syntology_url":"https://syntology.ai/paper/1608.06111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.06111"}},"official":{"repos":["mdtux89/amr-evaluation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/introduction-to-the-conll-2003-shared-task","slug":"introduction-to-the-conll-2003-shared-task","title":"Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition","date":"2003-06-12","arxiv_id":"cs/0306050","repositories_listed":4,"syntology":null},{"url":"/paper/rita-automatic-framework-for-designing-of","slug":"rita-automatic-framework-for-designing-of","title":"RITA: Automatic Framework for Designing of Resilient IoT Applications","date":"2024-11-27","arxiv_id":"2411.18324","repositories_listed":3,"syntology":null},{"url":"/paper/diffusionner-boundary-diffusion-for-named","slug":"diffusionner-boundary-diffusion-for-named","title":"DiffusionNER: Boundary Diffusion for Named Entity Recognition","date":"2023-05-22","arxiv_id":"2305.13298","repositories_listed":3,"syntology":null},{"url":"/paper/finer-financial-named-entity-recognition","slug":"finer-financial-named-entity-recognition","title":"FiNER-ORD: Financial Named Entity Recognition Open Research Dataset","date":"2023-02-22","arxiv_id":"2302.11157","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/finer-financial-named-entity-recognition#ran","syntology_url":"https://syntology.ai/paper/2302.11157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11157"}},"official":{"repos":["gtfintechlab/finer","gtfintechlab/finer-ord"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/xlm-v-overcoming-the-vocabulary-bottleneck-in","slug":"xlm-v-overcoming-the-vocabulary-bottleneck-in","title":"XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models","date":"2023-01-25","arxiv_id":"2301.10472","repositories_listed":3,"syntology":null},{"url":"/paper/atco2-corpus-a-large-scale-dataset-for","slug":"atco2-corpus-a-large-scale-dataset-for","title":"ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications","date":"2022-11-08","arxiv_id":"2211.04054","repositories_listed":3,"syntology":null},{"url":"/paper/chinesebert-chinese-pretraining-enhanced-by","slug":"chinesebert-chinese-pretraining-enhanced-by","title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information","date":"2021-06-30","arxiv_id":"2106.16038","repositories_listed":3,"syntology":null},{"url":"/paper/improving-named-entity-recognition-by","slug":"improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","arxiv_id":"2105.03654","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-named-entity-recognition-by#ran","syntology_url":"https://syntology.ai/paper/2105.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03654"}},"official":{"repos":["modelscope/adaseq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-analysis-of-simple-data-augmentation-for","slug":"an-analysis-of-simple-data-augmentation-for","title":"An Analysis of Simple Data Augmentation for Named Entity Recognition","date":"2020-10-22","arxiv_id":"2010.11683","repositories_listed":3,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-analysis-of-simple-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2010.11683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11683"}},"official":null}},{"url":"/paper/parsbert-transformer-based-model-for-persian","slug":"parsbert-transformer-based-model-for-persian","title":"ParsBERT: Transformer-based Model for Persian Language Understanding","date":"2020-05-26","arxiv_id":"2005.12515","repositories_listed":3,"syntology":null},{"url":"/paper/bertweet-a-pre-trained-language-model-for","slug":"bertweet-a-pre-trained-language-model-for","title":"BERTweet: A pre-trained language model for English Tweets","date":"2020-05-20","arxiv_id":"2005.10200","repositories_listed":3,"syntology":null},{"url":"/paper/mad-x-an-adapter-based-framework-for-multi","slug":"mad-x-an-adapter-based-framework-for-multi","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","date":"2020-04-30","arxiv_id":"2005.00052","repositories_listed":3,"syntology":null},{"url":"/paper/beheshti-ner-persian-named-entity-recognition","slug":"beheshti-ner-persian-named-entity-recognition","title":"Beheshti-NER: Persian Named Entity Recognition Using BERT","date":"2020-03-19","arxiv_id":"2003.08875","repositories_listed":3,"syntology":null},{"url":"/paper/parallel-sequence-tagging-for-concept","slug":"parallel-sequence-tagging-for-concept","title":"Parallel sequence tagging for concept recognition","date":"2020-03-16","arxiv_id":"2003.07424","repositories_listed":3,"syntology":null},{"url":"/paper/cluener2020-fine-grained-name-entity","slug":"cluener2020-fine-grained-name-entity","title":"CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese","date":"2020-01-13","arxiv_id":"2001.04351","repositories_listed":3,"syntology":null},{"url":"/paper/multi-hop-question-answering-via-reasoning","slug":"multi-hop-question-answering-via-reasoning","title":"Multi-hop Question Answering via Reasoning Chains","date":"2019-10-07","arxiv_id":"1910.02610","repositories_listed":3,"syntology":null},{"url":"/paper/nested-named-entity-recognition-via-second","slug":"nested-named-entity-recognition-via-second","title":"Nested Named Entity Recognition via Second-best Sequence Learning and Decoding","date":"2019-09-05","arxiv_id":"1909.02250","repositories_listed":3,"syntology":null},{"url":"/paper/advancing-nlp-with-cognitive-language","slug":"advancing-nlp-with-cognitive-language","title":"Advancing NLP with Cognitive Language Processing Signals","date":"2019-04-04","arxiv_id":"1904.02682","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/advancing-nlp-with-cognitive-language#ran","syntology_url":"https://syntology.ai/paper/1904.02682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02682"}},"official":{"repos":["DS3Lab/ner-at-first-sight","DS3Lab/zuco-nlp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/linspector-multilingual-probing-tasks-for","slug":"linspector-multilingual-probing-tasks-for","title":"LINSPECTOR: Multilingual Probing Tasks for Word Representations","date":"2019-03-22","arxiv_id":"1903.09442","repositories_listed":3,"syntology":null},{"url":"/paper/empower-sequence-labeling-with-task-aware","slug":"empower-sequence-labeling-with-task-aware","title":"Empower Sequence Labeling with Task-Aware Neural Language Model","date":"2017-09-13","arxiv_id":"1709.04109","repositories_listed":3,"syntology":null},{"url":"/paper/semi-supervised-multitask-learning-for","slug":"semi-supervised-multitask-learning-for","title":"Semi-supervised Multitask Learning for Sequence Labeling","date":"2017-04-24","arxiv_id":"1704.07156","repositories_listed":3,"syntology":null},{"url":"/paper/multimodal-llms-for-ocr-ocr-post-correction","slug":"multimodal-llms-for-ocr-ocr-post-correction","title":"Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents","date":"2025-04-01","arxiv_id":"2504.00414","repositories_listed":2,"syntology":null},{"url":"/paper/whisperner-unified-open-named-entity-and","slug":"whisperner-unified-open-named-entity-and","title":"WhisperNER: Unified Open Named Entity and Speech Recognition","date":"2024-09-12","arxiv_id":"2409.08107","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-grounded-multimodal-named-entity","slug":"advancing-grounded-multimodal-named-entity","title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","date":"2024-06-11","arxiv_id":"2406.07268","repositories_listed":2,"syntology":null},{"url":"/paper/do-english-named-entity-recognizers-work-well","slug":"do-english-named-entity-recognizers-work-well","title":"Do \"English\" Named Entity Recognizers Work Well on Global Englishes?","date":"2024-04-20","arxiv_id":"2404.13465","repositories_listed":2,"syntology":null},{"url":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-negative-instances-for-generative","slug":"rethinking-negative-instances-for-generative","title":"Rethinking Negative Instances for Generative Named Entity Recognition","date":"2024-02-26","arxiv_id":"2402.16602","repositories_listed":2,"syntology":null},{"url":"/paper/llms-as-bridges-reformulating-grounded","slug":"llms-as-bridges-reformulating-grounded","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","date":"2024-02-15","arxiv_id":"2402.09989","repositories_listed":2,"syntology":null},{"url":"/paper/def2vec-extensible-word-embeddings-from","slug":"def2vec-extensible-word-embeddings-from","title":"Def2Vec: Extensible Word Embeddings from Dictionary Definitions","date":"2023-12-16","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/learn-or-recall-revisiting-incremental","slug":"learn-or-recall-revisiting-incremental","title":"Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models","date":"2023-12-13","arxiv_id":"2312.07887","repositories_listed":2,"syntology":null},{"url":"/paper/universal-ner-a-gold-standard-multilingual-1","slug":"universal-ner-a-gold-standard-multilingual-1","title":"Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark","date":"2023-11-15","arxiv_id":"2311.09122","repositories_listed":2,"syntology":null},{"url":"/paper/gliner-generalist-model-for-named-entity","slug":"gliner-generalist-model-for-named-entity","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","date":"2023-11-14","arxiv_id":"2311.08526","repositories_listed":2,"syntology":null},{"url":"/paper/reading-order-matters-information-extraction","slug":"reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/puoberta-training-and-evaluation-of-a-curated","slug":"puoberta-training-and-evaluation-of-a-curated","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","date":"2023-10-13","arxiv_id":"2310.09141","repositories_listed":2,"syntology":null},{"url":"/paper/label-supervised-llama-finetuning","slug":"label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-hungarian-text-processing-with","slug":"advancing-hungarian-text-processing-with","title":"Advancing Hungarian Text Processing with HuSpaCy: Efficient and Accurate NLP Pipelines","date":"2023-08-24","arxiv_id":"2308.12635","repositories_listed":2,"syntology":null},{"url":"/paper/universalner-targeted-distillation-from-large","slug":"universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","arxiv_id":"2308.03279","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/universalner-targeted-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2308.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03279"}},"official":null}},{"url":"/paper/streamlining-social-media-information","slug":"streamlining-social-media-information","title":"Streamlining Social Media Information Retrieval for COVID-19 Research with Deep Learning","date":"2023-06-28","arxiv_id":"2306.16001","repositories_listed":2,"syntology":null},{"url":"/paper/bgglue-a-bulgarian-general-language","slug":"bgglue-a-bulgarian-general-language","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","date":"2023-06-04","arxiv_id":"2306.02349","repositories_listed":2,"syntology":null},{"url":"/paper/learning-in-context-learning-for-named-entity","slug":"learning-in-context-learning-for-named-entity","title":"Learning In-context Learning for Named Entity Recognition","date":"2023-05-18","arxiv_id":"2305.11038","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/learning-in-context-learning-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/2305.11038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11038"}},"official":{"repos":["chen700564/metaner-icl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","repositories_listed":2,"syntology":null},{"url":"/paper/findvehicle-and-vehiclefinder-a-ner-dataset","slug":"findvehicle-and-vehiclefinder-a-ner-dataset","title":"FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval system","date":"2023-04-21","arxiv_id":"2304.10893","repositories_listed":2,"syntology":null},{"url":"/paper/gpt-ner-named-entity-recognition-via-large","slug":"gpt-ner-named-entity-recognition-via-large","title":"GPT-NER: Named Entity Recognition via Large Language Models","date":"2023-04-20","arxiv_id":"2304.10428","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-ner-named-entity-recognition-via-large#ran","syntology_url":"https://syntology.ai/paper/2304.10428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10428"}},"official":{"repos":["shuhewang1998/gpt-ner"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","repositories_listed":2,"syntology":null},{"url":"/paper/type-aware-decomposed-framework-for-few-shot","slug":"type-aware-decomposed-framework-for-few-shot","title":"Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition","date":"2023-02-13","arxiv_id":"2302.06397","repositories_listed":2,"syntology":null},{"url":"/paper/foresight-deep-generative-modelling-of","slug":"foresight-deep-generative-modelling-of","title":"Foresight -- Generative Pretrained Transformer (GPT) for Modelling of Patient Timelines using EHRs","date":"2022-12-13","arxiv_id":"2212.08072","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/foresight-deep-generative-modelling-of#ran","syntology_url":"https://syntology.ai/paper/2212.08072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08072"}},"official":{"repos":["cogstack/foresight"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/genius-sketch-based-language-model-pre","slug":"genius-sketch-based-language-model-pre","title":"GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation","date":"2022-11-18","arxiv_id":"2211.10330","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-boundary-aware-language-model","slug":"unsupervised-boundary-aware-language-model","title":"Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling","date":"2022-10-27","arxiv_id":"2210.15231","repositories_listed":2,"syntology":null},{"url":"/paper/on-cross-domain-pre-trained-language-models","slug":"on-cross-domain-pre-trained-language-models","title":"Exploring the Value of Pre-trained Language Models for Clinical Named Entity Recognition","date":"2022-10-23","arxiv_id":"2210.12770","repositories_listed":2,"syntology":null},{"url":"/paper/simple-yet-powerful-an-overlooked-1","slug":"simple-yet-powerful-an-overlooked-1","title":"Simple Yet Powerful: An Overlooked Architecture for Nested Named Entity Recognition","date":"2022-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/fijo-a-french-insurance-soft-skill-detection","slug":"fijo-a-french-insurance-soft-skill-detection","title":"\"FIJO\": a French Insurance Soft Skill Detection Dataset","date":"2022-04-11","arxiv_id":"2204.05208","repositories_listed":2,"syntology":null},{"url":"/paper/miner-improving-out-of-vocabulary-named-1","slug":"miner-improving-out-of-vocabulary-named-1","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","date":"2022-04-09","arxiv_id":"2204.04391","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/miner-improving-out-of-vocabulary-named-1#ran","syntology_url":"https://syntology.ai/paper/2204.04391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.04391"}},"official":{"repos":["beyonderxx/miner"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rumedbench-a-russian-medical-language","slug":"rumedbench-a-russian-medical-language","title":"RuMedBench: A Russian Medical Language Understanding Benchmark","date":"2022-01-17","arxiv_id":"2201.06499","repositories_listed":2,"syntology":null},{"url":"/paper/label-descriptive-patterns-and-their","slug":"label-descriptive-patterns-and-their","title":"Label-Descriptive Patterns and Their Application to Characterizing Classification Errors","date":"2021-10-18","arxiv_id":"2110.09599","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/label-descriptive-patterns-and-their#ran","syntology_url":"https://syntology.ai/paper/2110.09599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09599"}},"official":{"repos":["uds-lsv/premise"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reproducing-ner-and-pos-when-nothing-is","slug":"reproducing-ner-and-pos-when-nothing-is","title":"reproducing \"ner and pos when nothing is capitalized\"","date":"2021-09-17","arxiv_id":"2109.08396","repositories_listed":2,"syntology":null},{"url":"/paper/slot-filling-for-biomedical-information","slug":"slot-filling-for-biomedical-information","title":"Slot Filling for Biomedical Information Extraction","date":"2021-09-17","arxiv_id":"2109.08564","repositories_listed":2,"syntology":null},{"url":"/paper/everything-is-all-it-takes-a-multipronged","slug":"everything-is-all-it-takes-a-multipronged","title":"Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction","date":"2021-09-14","arxiv_id":"2109.06798","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/everything-is-all-it-takes-a-multipronged#ran","syntology_url":"https://syntology.ai/paper/2109.06798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06798"}},"official":{"repos":["shijie-wu/crosslingual-nlp","kentonmurray/arabicdetokenizer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cblue-a-chinese-biomedical-language","slug":"cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","date":"2021-06-15","arxiv_id":"2106.08087","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cblue-a-chinese-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/2106.08087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08087"}},"official":{"repos":["cbluebenchmark/cblue"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/how-low-is-too-low-a-computational","slug":"how-low-is-too-low-a-computational","title":"How Low is Too Low? A Computational Perspective on Extremely Low-Resource Languages","date":"2021-05-30","arxiv_id":"2105.14515","repositories_listed":2,"syntology":null},{"url":"/paper/bertifying-the-hidden-markov-model-for-multi","slug":"bertifying-the-hidden-markov-model-for-multi","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","date":"2021-05-26","arxiv_id":"2105.12848","repositories_listed":2,"syntology":{"n":20,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/bertifying-the-hidden-markov-model-for-multi#ran","syntology_url":"https://syntology.ai/paper/2105.12848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12848"}},"official":{"repos":["Yinghao-Li/CHMM-ALT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/optimizing-small-berts-trained-for-german-ner","slug":"optimizing-small-berts-trained-for-german-ner","title":"Optimizing small BERTs trained for German NER","date":"2021-04-23","arxiv_id":"2104.11559","repositories_listed":2,"syntology":null},{"url":"/paper/earnings-21-a-practical-benchmark-for-asr-in","slug":"earnings-21-a-practical-benchmark-for-asr-in","title":"Earnings-21: A Practical Benchmark for ASR in the Wild","date":"2021-04-22","arxiv_id":"2104.11348","repositories_listed":2,"syntology":null},{"url":"/paper/electramed-a-new-pre-trained-language","slug":"electramed-a-new-pre-trained-language","title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","date":"2021-04-19","arxiv_id":"2104.09585","repositories_listed":2,"syntology":null},{"url":"/paper/mt6-multilingual-pretrained-text-to-text","slug":"mt6-multilingual-pretrained-text-to-text","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","date":"2021-04-18","arxiv_id":"2104.08692","repositories_listed":2,"syntology":null},{"url":"/paper/metaxl-meta-representation-transformation-for","slug":"metaxl-meta-representation-transformation-for","title":"MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning","date":"2021-04-16","arxiv_id":"2104.07908","repositories_listed":2,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/metaxl-meta-representation-transformation-for#ran","syntology_url":"https://syntology.ai/paper/2104.07908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07908"}},"official":{"repos":["microsoft/MetaXL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/alephbert-a-hebrew-large-pre-trained-language","slug":"alephbert-a-hebrew-large-pre-trained-language","title":"AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With","date":"2021-04-08","arxiv_id":"2104.04052","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alephbert-a-hebrew-large-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2104.04052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.04052"}},"official":{"repos":["OnlpLab/Hebrew-Sentiment-Data"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/masakhaner-named-entity-recognition-for","slug":"masakhaner-named-entity-recognition-for","title":"MasakhaNER: Named Entity Recognition for African Languages","date":"2021-03-22","arxiv_id":"2103.11811","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/masakhaner-named-entity-recognition-for#ran","syntology_url":"https://syntology.ai/paper/2103.11811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11811"}},"official":{"repos":["masakhane-io/masakhane-ner"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/structured-prediction-as-translation-between-1","slug":"structured-prediction-as-translation-between-1","title":"Structured Prediction as Translation between Augmented Natural Languages","date":"2021-01-14","arxiv_id":"2101.05779","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-named-entity-recognition-a","slug":"few-shot-named-entity-recognition-a","title":"Few-Shot Named Entity Recognition: A Comprehensive Study","date":"2020-12-29","arxiv_id":"2012.14978","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-deep-neural-networks-with","slug":"enhancing-deep-neural-networks-with","title":"Enhancing deep neural networks with morphological information","date":"2020-11-24","arxiv_id":"2011.12432","repositories_listed":2,"syntology":null},{"url":"/paper/interpretable-multi-dataset-evaluation-for","slug":"interpretable-multi-dataset-evaluation-for","title":"Interpretable Multi-dataset Evaluation for Named Entity Recognition","date":"2020-11-13","arxiv_id":"2011.06854","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-multi-dataset-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2011.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.06854"}},"official":{"repos":["neulab/InterpretEval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/identifying-incorrect-labels-in-the-conll","slug":"identifying-incorrect-labels-in-the-conll","title":"Identifying Incorrect Labels in the CoNLL-2003 Corpus","date":"2020-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/two-are-better-than-one-joint-entity-and","slug":"two-are-better-than-one-joint-entity-and","title":"Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders","date":"2020-10-08","arxiv_id":"2010.03851","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/two-are-better-than-one-joint-entity-and#ran","syntology_url":"https://syntology.ai/paper/2010.03851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03851"}},"official":{"repos":["LorrinWWW/two-are-better-than-one"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/dwie-an-entity-centric-dataset-for-multi-task","slug":"dwie-an-entity-centric-dataset-for-multi-task","title":"DWIE: an entity-centric dataset for multi-task document-level information extraction","date":"2020-09-26","arxiv_id":"2009.12626","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dwie-an-entity-centric-dataset-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2009.12626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12626"}},"official":{"repos":["klimzaporojets/DWIE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"syntology_records":35,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":118,"papers_where_code_ran_first_page":"/task/named-entity-recognition-1/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":26,"url":"/task/named-entity-recognition-1/papers/2","json":"/task/named-entity-recognition-1/papers/2.json","rows":100},{"order":"archive","page":3,"of":26,"url":"/task/named-entity-recognition-1/papers/3","json":"/task/named-entity-recognition-1/papers/3.json","rows":100},{"order":"archive","page":4,"of":26,"url":"/task/named-entity-recognition-1/papers/4","json":"/task/named-entity-recognition-1/papers/4.json","rows":100},{"order":"archive","page":5,"of":26,"url":"/task/named-entity-recognition-1/papers/5","json":"/task/named-entity-recognition-1/papers/5.json","rows":100},{"order":"archive","page":6,"of":26,"url":"/task/named-entity-recognition-1/papers/6","json":"/task/named-entity-recognition-1/papers/6.json","rows":100},{"order":"archive","page":7,"of":26,"url":"/task/named-entity-recognition-1/papers/7","json":"/task/named-entity-recognition-1/papers/7.json","rows":100},{"order":"archive","page":8,"of":26,"url":"/task/named-entity-recognition-1/papers/8","json":"/task/named-entity-recognition-1/papers/8.json","rows":100},{"order":"archive","page":9,"of":26,"url":"/task/named-entity-recognition-1/papers/9","json":"/task/named-entity-recognition-1/papers/9.json","rows":100},{"order":"archive","page":10,"of":26,"url":"/task/named-entity-recognition-1/papers/10","json":"/task/named-entity-recognition-1/papers/10.json","rows":100},{"order":"archive","page":11,"of":26,"url":"/task/named-entity-recognition-1/papers/11","json":"/task/named-entity-recognition-1/papers/11.json","rows":100},{"order":"archive","page":12,"of":26,"url":"/task/named-entity-recognition-1/papers/12","json":"/task/named-entity-recognition-1/papers/12.json","rows":100},{"order":"archive","page":13,"of":26,"url":"/task/named-entity-recognition-1/papers/13","json":"/task/named-entity-recognition-1/papers/13.json","rows":100},{"order":"archive","page":14,"of":26,"url":"/task/named-entity-recognition-1/papers/14","json":"/task/named-entity-recognition-1/papers/14.json","rows":100},{"order":"archive","page":15,"of":26,"url":"/task/named-entity-recognition-1/papers/15","json":"/task/named-entity-recognition-1/papers/15.json","rows":100},{"order":"archive","page":16,"of":26,"url":"/task/named-entity-recognition-1/papers/16","json":"/task/named-entity-recognition-1/papers/16.json","rows":100},{"order":"archive","page":17,"of":26,"url":"/task/named-entity-recognition-1/papers/17","json":"/task/named-entity-recognition-1/papers/17.json","rows":100},{"order":"archive","page":18,"of":26,"url":"/task/named-entity-recognition-1/papers/18","json":"/task/named-entity-recognition-1/papers/18.json","rows":100},{"order":"archive","page":19,"of":26,"url":"/task/named-entity-recognition-1/papers/19","json":"/task/named-entity-recognition-1/papers/19.json","rows":100},{"order":"archive","page":20,"of":26,"url":"/task/named-entity-recognition-1/papers/20","json":"/task/named-entity-recognition-1/papers/20.json","rows":100},{"order":"archive","page":21,"of":26,"url":"/task/named-entity-recognition-1/papers/21","json":"/task/named-entity-recognition-1/papers/21.json","rows":100},{"order":"archive","page":22,"of":26,"url":"/task/named-entity-recognition-1/papers/22","json":"/task/named-entity-recognition-1/papers/22.json","rows":100},{"order":"archive","page":23,"of":26,"url":"/task/named-entity-recognition-1/papers/23","json":"/task/named-entity-recognition-1/papers/23.json","rows":100},{"order":"archive","page":24,"of":26,"url":"/task/named-entity-recognition-1/papers/24","json":"/task/named-entity-recognition-1/papers/24.json","rows":100},{"order":"archive","page":25,"of":26,"url":"/task/named-entity-recognition-1/papers/25","json":"/task/named-entity-recognition-1/papers/25.json","rows":100},{"order":"archive","page":26,"of":26,"url":"/task/named-entity-recognition-1/papers/26","json":"/task/named-entity-recognition-1/papers/26.json","rows":60},{"order":"ran","page":1,"of":2,"url":"/task/named-entity-recognition-1/papers/ran/1","json":"/task/named-entity-recognition-1/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/named-entity-recognition-1/papers/ran/2","json":"/task/named-entity-recognition-1/papers/ran/2.json","rows":18}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"e469ae59f76ea57924ec345bfd65ed6f52130c95b31f08b1aa33436ae26f0d46","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}